mirror of https://github.com/ollama/ollama.git
58245413f4
feat: add new Ollama engine using ggml through cgo This change introduces a new way to run pretrained models. It introduces 3 high level interfaces and a bunch of smaller helper interfaces to facilitate this. - `model.Model` defines the interface for a model architecture. Models such as `llama` and `mllama`, which are provided as examples, can implement the model's forward propagation in the `Forward` method. This method will be called to generate completions. This interface can be found in `model/model.go` - `ml.Backend` defines the interface for a backend tensor library, in this case `ggml`. Among other things, a Backend is responsible for loading a pretrained model into hardware (GPU, CPU, etc) and providing an interface for Models to access loaded tensors. This interface can be found in `ml/backend.go` - `ml.Tensor` defines the interface for a tensor and tensor operations This is the first implementation of the new engine. Follow up PRs will implement more features: - non-greedy sampling (#8410) - integration with Ollama and KV caching (#8301) - more model support (#9080) with more coming soon Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com> |
||
|---|---|---|
| .. | ||
| testdata | ||
| alfred.gotmpl | ||
| alfred.json | ||
| alpaca.gotmpl | ||
| alpaca.json | ||
| chatml.gotmpl | ||
| chatml.json | ||
| chatqa.gotmpl | ||
| chatqa.json | ||
| codellama-70b-instruct.gotmpl | ||
| codellama-70b-instruct.json | ||
| command-r.gotmpl | ||
| command-r.json | ||
| falcon-instruct.gotmpl | ||
| falcon-instruct.json | ||
| gemma-instruct.gotmpl | ||
| gemma-instruct.json | ||
| granite-instruct.gotmpl | ||
| granite-instruct.json | ||
| index.json | ||
| llama2-chat.gotmpl | ||
| llama2-chat.json | ||
| llama3-instruct.gotmpl | ||
| llama3-instruct.json | ||
| magicoder.gotmpl | ||
| magicoder.json | ||
| mistral-instruct.gotmpl | ||
| mistral-instruct.json | ||
| openchat.gotmpl | ||
| openchat.json | ||
| phi-3.gotmpl | ||
| phi-3.json | ||
| solar-instruct.gotmpl | ||
| solar-instruct.json | ||
| starcoder2-instruct.gotmpl | ||
| starcoder2-instruct.json | ||
| template.go | ||
| template_test.go | ||
| vicuna.gotmpl | ||
| vicuna.json | ||
| zephyr.gotmpl | ||
| zephyr.json | ||